Cura 1T: A Dedicated LLM for Medical Agents
actAVA AI · hf · 2026-07-20
To address the complex communication, clinical reasoning, and workflow execution demands of the healthcare sector, actAVA AI has released the specialized LLM Cura 1T. The model is capable of handling patient consultations, image-text clinical reasoning, interactive diagnosis, and EHR (Electronic Health Record) tool calling.
Technical Highlights:
- Human-in-the-loop Self-evolution Cycle: Model training incorporates an agentic planning mechanism. In each evolution round, the training Agent plans target capabilities, trains the model, evaluates benchmark trajectories, and optimizes data mixture ratios based on observed failures.
- Precision Data-Driven: Capabilities are enhanced through targeted synthetic data and curated examples, avoiding the task degradation often caused by updating with generic medical data.
- Performance: In medical evaluation suites, Cura 1T ranks among frontier models while remaining competitive on out-of-domain reasoning and general agent benchmarks.
Related event: actAVA AI Launches Cura, a 1T-Parameter Medical Agent Model(2 posts)→
More from Models
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27
- Across 7 tasks, highest reasoning setting isn't the best for most open models — keunwoochoi · 2026-10-27